* [PATCH 1/6] sched_ext: Split task_should_reenq() into local and user variants
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
@ 2026-03-13 11:31 ` Tejun Heo
2026-03-13 11:31 ` [PATCH 2/6] sched_ext: Add scx_vet_enq_flags() and plumb dsq_id into preamble Tejun Heo
` (7 subsequent siblings)
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 11:31 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
Split task_should_reenq() into local_task_should_reenq() and
user_task_should_reenq(). The local variant takes reenq_flags by pointer.
No functional change. This prepares for SCX_ENQ_IMMED which will add
IMMED-specific logic to the local variant.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index e7ab3647e35f..774c012831e6 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3725,13 +3725,10 @@ static void process_ddsp_deferred_locals(struct rq *rq)
}
}
-static bool task_should_reenq(struct task_struct *p, u64 reenq_flags, u32 *reason)
+static bool local_task_should_reenq(struct task_struct *p, u64 *reenq_flags, u32 *reason)
{
*reason = SCX_TASK_REENQ_KFUNC;
-
- if (reenq_flags & SCX_REENQ_ANY)
- return true;
- return false;
+ return *reenq_flags & SCX_REENQ_ANY;
}
static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
@@ -3769,7 +3766,7 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
if (!scx_is_descendant(task_sch, sch))
continue;
- if (!task_should_reenq(p, reenq_flags, &reason))
+ if (!local_task_should_reenq(p, &reenq_flags, &reason))
continue;
dispatch_dequeue(rq, p);
@@ -3826,6 +3823,12 @@ static void process_deferred_reenq_locals(struct rq *rq)
}
}
+static bool user_task_should_reenq(struct task_struct *p, u64 reenq_flags, u32 *reason)
+{
+ *reason = SCX_TASK_REENQ_KFUNC;
+ return reenq_flags & SCX_REENQ_ANY;
+}
+
static void reenq_user(struct rq *rq, struct scx_dispatch_q *dsq, u64 reenq_flags)
{
struct rq *locked_rq = rq;
@@ -3846,7 +3849,7 @@ static void reenq_user(struct rq *rq, struct scx_dispatch_q *dsq, u64 reenq_flag
if (!p)
break;
- if (!task_should_reenq(p, reenq_flags, &reason))
+ if (!user_task_should_reenq(p, reenq_flags, &reason))
continue;
task_rq = task_rq(p);
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 2/6] sched_ext: Add scx_vet_enq_flags() and plumb dsq_id into preamble
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
2026-03-13 11:31 ` [PATCH 1/6] sched_ext: Split task_should_reenq() into local and user variants Tejun Heo
@ 2026-03-13 11:31 ` Tejun Heo
2026-03-13 11:31 ` [PATCH 3/6] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (6 subsequent siblings)
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 11:31 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
Add scx_vet_enq_flags() stub and call it from scx_dsq_insert_preamble() and
scx_dsq_move(). Pass dsq_id into preamble so the vetting function can
validate flag and DSQ combinations.
No functional change. This prepares for SCX_ENQ_IMMED which will populate the
vetting function.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 774c012831e6..2f59265b9b57 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7530,8 +7530,13 @@ void __init init_sched_ext_class(void)
/********************************************************************************
* Helpers that can be called from the BPF scheduler.
*/
+static bool scx_vet_enq_flags(struct scx_sched *sch, u64 dsq_id, u64 enq_flags)
+{
+ return true;
+}
+
static bool scx_dsq_insert_preamble(struct scx_sched *sch, struct task_struct *p,
- u64 enq_flags)
+ u64 dsq_id, u64 enq_flags)
{
if (!scx_kf_allowed(sch, SCX_KF_ENQUEUE | SCX_KF_DISPATCH))
return false;
@@ -7554,6 +7559,9 @@ static bool scx_dsq_insert_preamble(struct scx_sched *sch, struct task_struct *p
return false;
}
+ if (!scx_vet_enq_flags(sch, dsq_id, enq_flags))
+ return false;
+
return true;
}
@@ -7635,7 +7643,7 @@ __bpf_kfunc bool scx_bpf_dsq_insert___v2(struct task_struct *p, u64 dsq_id,
if (unlikely(!sch))
return false;
- if (!scx_dsq_insert_preamble(sch, p, enq_flags))
+ if (!scx_dsq_insert_preamble(sch, p, dsq_id, enq_flags))
return false;
if (slice)
@@ -7661,7 +7669,7 @@ __bpf_kfunc void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id,
static bool scx_dsq_insert_vtime(struct scx_sched *sch, struct task_struct *p,
u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags)
{
- if (!scx_dsq_insert_preamble(sch, p, enq_flags))
+ if (!scx_dsq_insert_preamble(sch, p, dsq_id, enq_flags))
return false;
if (slice)
@@ -7788,6 +7796,9 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
!scx_kf_allowed(sch, SCX_KF_DISPATCH))
return false;
+ if (!scx_vet_enq_flags(sch, dsq_id, enq_flags))
+ return false;
+
/*
* If the BPF scheduler keeps calling this function repeatedly, it can
* cause similar live-lock conditions as consume_dispatch_q().
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 3/6] sched_ext: Implement SCX_ENQ_IMMED
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
2026-03-13 11:31 ` [PATCH 1/6] sched_ext: Split task_should_reenq() into local and user variants Tejun Heo
2026-03-13 11:31 ` [PATCH 2/6] sched_ext: Add scx_vet_enq_flags() and plumb dsq_id into preamble Tejun Heo
@ 2026-03-13 11:31 ` Tejun Heo
2026-03-13 19:15 ` Andrea Righi
2026-03-13 11:31 ` [PATCH 4/6] sched_ext: Plumb enq_flags through the consume path Tejun Heo
` (5 subsequent siblings)
8 siblings, 1 reply; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 11:31 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
Add SCX_ENQ_IMMED enqueue flag for local DSQ insertions. Once a task is
dispatched with IMMED, it either gets on the CPU immediately and stays on it,
or gets reenqueued back to the BPF scheduler. It will never linger on a local
DSQ behind other tasks or on a CPU taken by a higher-priority class.
rq_is_open() uses rq->next_class to determine whether the rq is available,
and wakeup_preempt_scx() triggers reenqueue when a higher-priority class task
arrives. These capture all higher class preemptions. Combined with reenqueue
points in the dispatch path, all cases where an IMMED task would not execute
immediately are covered.
SCX_TASK_IMMED persists in p->scx.flags until the next fresh enqueue, so the
guarantee survives SAVE/RESTORE cycles. If preempted while running,
put_prev_task_scx() reenqueues through ops.enqueue() with
SCX_TASK_REENQ_PREEMPTED instead of silently placing the task back on the
local DSQ.
This enables tighter scheduling latency control by preventing tasks from
piling up on local DSQs. It also enables opportunistic CPU sharing across
sub-schedulers - without this, a sub-scheduler can stuff the local DSQ of a
shared CPU, making it difficult for others to use.
v2: - Rewrite is_curr_done() as rq_is_open() using rq->next_class and
implement wakeup_preempt_scx() to achieve complete coverage of all
cases where IMMED tasks could get stranded.
- Track IMMED persistently in p->scx.flags and reenqueue
preempted-while-running tasks through ops.enqueue().
- Bound deferred reenq cycles (SCX_REENQ_LOCAL_MAX_REPEAT).
- Misc renames, documentation.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
include/linux/sched/ext.h | 5 +
kernel/sched/ext.c | 271 +++++++++++++++++++++--
kernel/sched/ext_internal.h | 47 ++++
kernel/sched/sched.h | 2 +
tools/sched_ext/include/scx/compat.bpf.h | 5 +
5 files changed, 311 insertions(+), 19 deletions(-)
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 60a4f65d0174..602dc83cab36 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -100,6 +100,7 @@ enum scx_ent_flags {
SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */
SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */
SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */
+ SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */
/*
* Bits 8 and 9 are used to carry task state:
@@ -125,6 +126,8 @@ enum scx_ent_flags {
*
* NONE not being reenqueued
* KFUNC reenqueued by scx_bpf_dsq_reenq() and friends
+ * IMMED reenqueued due to failed ENQ_IMMED
+ * PREEMPTED preempted while running
*/
SCX_TASK_REENQ_REASON_SHIFT = 12,
SCX_TASK_REENQ_REASON_BITS = 2,
@@ -132,6 +135,8 @@ enum scx_ent_flags {
SCX_TASK_REENQ_NONE = 0 << SCX_TASK_REENQ_REASON_SHIFT,
SCX_TASK_REENQ_KFUNC = 1 << SCX_TASK_REENQ_REASON_SHIFT,
+ SCX_TASK_REENQ_IMMED = 2 << SCX_TASK_REENQ_REASON_SHIFT,
+ SCX_TASK_REENQ_PREEMPTED = 3 << SCX_TASK_REENQ_REASON_SHIFT,
/* iteration cursor, not a task */
SCX_TASK_CURSOR = 1 << 31,
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2f59265b9b57..85cdb65a5a66 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -406,6 +406,62 @@ static bool bypass_dsp_enabled(struct scx_sched *sch)
return unlikely(atomic_read(&sch->bypass_dsp_enable_depth));
}
+/**
+ * rq_is_open - Is the rq available for immediate execution of an SCX task?
+ * @rq: rq to test
+ * @enq_flags: optional %SCX_ENQ_* of the task being enqueued
+ *
+ * Returns %true if @rq is currently open for executing an SCX task. After a
+ * %false return, @rq is guaranateed to invoke SCX dispatch path at least once
+ * before going to idle and not inserting a task into @rq's local DSQ after a
+ * %false return doesn't cause @rq to stall.
+ */
+static bool rq_is_open(struct rq *rq, u64 enq_flags)
+{
+ lockdep_assert_rq_held(rq);
+
+ /*
+ * A higher-priority class task is either running or in the process of
+ * waking up on @rq.
+ */
+ if (sched_class_above(rq->next_class, &ext_sched_class))
+ return false;
+
+ /*
+ * @rq is either in transition to or in idle and there is no
+ * higher-priority class task waking up on it.
+ */
+ if (sched_class_above(&ext_sched_class, rq->next_class))
+ return true;
+
+ /*
+ * @rq is either picking, in transition to, or running an SCX task.
+ */
+
+ /*
+ * If we're in the dispatch path holding rq lock, $curr may or may not
+ * be ready depending on whether the on-going dispatch decides to extend
+ * $curr's slice. We say yes here and resolve it at the end of dispatch.
+ * See balance_one().
+ */
+ if (rq->scx.flags & SCX_RQ_IN_BALANCE)
+ return true;
+
+ /*
+ * %SCX_ENQ_PREEMPT clears $curr's slice if on SCX and kicks dispatch,
+ * so allow it to avoid spuriously triggering reenq on a combined
+ * PREEMPT|IMMED insertion.
+ */
+ if (enq_flags & SCX_ENQ_PREEMPT)
+ return true;
+
+ /*
+ * @rq is either in transition to or running an SCX task and can't go
+ * idle without another SCX dispatch cycle.
+ */
+ return false;
+}
+
/*
* scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX
* ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate
@@ -1220,6 +1276,16 @@ static void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq
}
}
+static void schedule_reenq_local(struct rq *rq, u64 reenq_flags)
+{
+ struct scx_sched *root = rcu_dereference_sched(scx_root);
+
+ if (WARN_ON_ONCE(!root))
+ return;
+
+ schedule_dsq_reenq(root, &rq->scx.local_dsq, reenq_flags);
+}
+
/**
* touch_core_sched - Update timestamp used for core-sched task ordering
* @rq: rq to read clock from, must be locked
@@ -1296,10 +1362,58 @@ static bool scx_dsq_priq_less(struct rb_node *node_a,
return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime);
}
-static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
+static void dsq_inc_nr(struct scx_dispatch_q *dsq, struct task_struct *p, u64 enq_flags)
{
/* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */
- WRITE_ONCE(dsq->nr, dsq->nr + delta);
+ WRITE_ONCE(dsq->nr, dsq->nr + 1);
+
+ /*
+ * Once @p reaches a local DSQ, it can only leave it by being dispatched
+ * to the CPU or dequeued. In both cases, the only way @p can go back to
+ * the BPF sched is through enqueueing. If being inserted into a local
+ * DSQ with IMMED, persist the state until the next enqueueing event in
+ * do_enqueue_task() so that we can maintain IMMED protection through
+ * e.g. SAVE/RESTORE cycles and slice extensions.
+ */
+ if (enq_flags & SCX_ENQ_IMMED) {
+ if (unlikely(dsq->id != SCX_DSQ_LOCAL)) {
+ WARN_ON_ONCE(!(enq_flags & SCX_ENQ_GDSQ_FALLBACK));
+ return;
+ }
+ p->scx.flags |= SCX_TASK_IMMED;
+ }
+
+ if (p->scx.flags & SCX_TASK_IMMED) {
+ struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
+
+ if (WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL))
+ return;
+
+ rq->scx.nr_immed++;
+
+ /*
+ * If @rq already had other tasks or the current task is not
+ * done yet, @p can't go on the CPU immediately. Re-enqueue.
+ */
+ if (unlikely(dsq->nr > 1 || !rq_is_open(rq, enq_flags)))
+ schedule_reenq_local(rq, 0);
+ }
+}
+
+static void dsq_dec_nr(struct scx_dispatch_q *dsq, struct task_struct *p)
+{
+ /* see dsq_inc_nr() */
+ WRITE_ONCE(dsq->nr, dsq->nr - 1);
+
+ if (p->scx.flags & SCX_TASK_IMMED) {
+ struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
+
+ if (WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL) ||
+ WARN_ON_ONCE(rq->scx.nr_immed <= 0))
+ return;
+
+ rq->scx.nr_immed--;
+ }
}
static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p)
@@ -1458,7 +1572,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct rq *rq,
WRITE_ONCE(dsq->seq, dsq->seq + 1);
p->scx.dsq_seq = dsq->seq;
- dsq_mod_nr(dsq, 1);
+ dsq_inc_nr(dsq, p, enq_flags);
p->scx.dsq = dsq;
/*
@@ -1512,7 +1626,7 @@ static void task_unlink_from_dsq(struct task_struct *p,
}
list_del_init(&p->scx.dsq_list.node);
- dsq_mod_nr(dsq, -1);
+ dsq_dec_nr(dsq, p);
if (!(dsq->id & SCX_DSQ_FLAG_BUILTIN) && dsq->first_task == p) {
struct task_struct *first_task;
@@ -1723,10 +1837,18 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED));
- /* rq migration */
+ /* internal movements - rq migration / RESTORE */
if (sticky_cpu == cpu_of(rq))
goto local_norefill;
+ /*
+ * Clear persistent TASK_IMMED for fresh enqueues, see dsq_inc_nr().
+ * Note that exiting and migration-disabled tasks that skip
+ * ops.enqueue() below will lose IMMED protection unless
+ * %SCX_OPS_ENQ_EXITING / %SCX_OPS_ENQ_MIGRATION_DISABLED are set.
+ */
+ p->scx.flags &= ~SCX_TASK_IMMED;
+
/*
* If !scx_rq_online(), we already told the BPF scheduler that the CPU
* is offline and are just running the hotplug path. Don't bother the
@@ -2032,6 +2154,30 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
return false;
}
+static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_flags)
+{
+ /*
+ * Preemption between SCX tasks is implemented by resetting the victim
+ * task's slice to 0 and triggering reschedule on the target CPU.
+ * Nothing to do.
+ */
+ if (p->sched_class == &ext_sched_class)
+ return;
+
+ /*
+ * Getting preempted by a higher-priority class. Reenqueue IMMED tasks.
+ * This captures all preemption cases including:
+ *
+ * - A SCX task is currently running.
+ *
+ * - @rq is waking from idle due to a SCX task waking to it.
+ *
+ * - A higher-priority wakes up while SCX dispatch is in progress.
+ */
+ if (rq->scx.nr_immed)
+ schedule_reenq_local(rq, 0);
+}
+
static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
struct scx_dispatch_q *src_dsq,
struct rq *dst_rq)
@@ -2049,7 +2195,7 @@ static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
else
list_add_tail(&p->scx.dsq_list.node, &dst_dsq->list);
- dsq_mod_nr(dst_dsq, 1);
+ dsq_inc_nr(dst_dsq, p, enq_flags);
p->scx.dsq = dst_dsq;
local_dsq_post_enq(dst_dsq, p, enq_flags);
@@ -2257,6 +2403,7 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
dst_dsq = find_global_dsq(sch, task_cpu(p));
dst_rq = src_rq;
+ enq_flags |= SCX_ENQ_GDSQ_FALLBACK;
}
} else {
/* no need to migrate if destination is a non-local DSQ */
@@ -2385,7 +2532,7 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
if (src_rq != dst_rq &&
unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
dispatch_enqueue(sch, rq, find_global_dsq(sch, task_cpu(p)), p,
- enq_flags | SCX_ENQ_CLEAR_OPSS);
+ enq_flags | SCX_ENQ_CLEAR_OPSS | SCX_ENQ_GDSQ_FALLBACK);
return;
}
@@ -2738,6 +2885,19 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
return false;
has_tasks:
+ /*
+ * @rq may have extra IMMED tasks without reenq scheduled:
+ *
+ * - rq_is_open() can't reliably tell when and how slice is going to be
+ * modified for $curr and allows IMMED tasks to be queued while
+ * dispatch is in progress.
+ *
+ * - A non-IMMED HEAD task can get queued in front of an IMMED task
+ * between the IMMED queueing and the subsequent scheduling event.
+ */
+ if (unlikely(rq->scx.local_dsq.nr > 1 && rq->scx.nr_immed))
+ schedule_reenq_local(rq, 0);
+
rq->scx.flags &= ~SCX_RQ_IN_BALANCE;
return true;
}
@@ -2859,11 +3019,17 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
* If @p has slice left and is being put, @p is getting
* preempted by a higher priority scheduler class or core-sched
* forcing a different task. Leave it at the head of the local
- * DSQ.
+ * DSQ unless it was an IMMED task. IMMED tasks should not
+ * linger on a busy CPU, reenqueue them to the BPF scheduler.
*/
if (p->scx.slice && !scx_bypassing(sch, cpu_of(rq))) {
- dispatch_enqueue(sch, rq, &rq->scx.local_dsq, p,
- SCX_ENQ_HEAD);
+ if (p->scx.flags & SCX_TASK_IMMED) {
+ p->scx.flags |= SCX_TASK_REENQ_PREEMPTED;
+ do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
+ p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+ } else {
+ dispatch_enqueue(sch, rq, &rq->scx.local_dsq, p, SCX_ENQ_HEAD);
+ }
goto switch_class;
}
@@ -3682,8 +3848,6 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p)
scx_disable_task(scx_task_sched(p), p);
}
-static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_flags) {}
-
static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
int scx_check_setscheduler(struct task_struct *p, int policy)
@@ -3725,9 +3889,45 @@ static void process_ddsp_deferred_locals(struct rq *rq)
}
}
+/*
+ * Determine whether @p should be reenqueued from a local DSQ.
+ *
+ * @reenq_flags is mutable and accumulates state across the DSQ walk:
+ *
+ * - %SCX_REENQ_TSR_NOT_FIRST: Set after the first task is visited. "First"
+ * tracks position in the DSQ list, not among IMMED tasks. A non-IMMED task at
+ * the head consumes the first slot.
+ *
+ * - %SCX_REENQ_TSR_RQ_OPEN: Set by reenq_local() before the walk if
+ * rq_is_open() is true.
+ *
+ * An IMMED task is kept (returns %false) only if it's the first task in the DSQ
+ * AND the current task is done — i.e. it will execute immediately. All other
+ * IMMED tasks are reenqueued. This means if a non-IMMED task sits at the head,
+ * every IMMED task behind it gets reenqueued.
+ *
+ * Reenqueued tasks go through ops.enqueue() with %SCX_ENQ_REENQ |
+ * %SCX_TASK_REENQ_IMMED. If the BPF scheduler dispatches back to the same local
+ * DSQ with %SCX_ENQ_IMMED while the CPU is still unavailable, this triggers
+ * another reenq cycle. Repetitions are bounded by %SCX_REENQ_LOCAL_MAX_REPEAT
+ * in process_deferred_reenq_locals().
+ */
static bool local_task_should_reenq(struct task_struct *p, u64 *reenq_flags, u32 *reason)
{
+ bool first;
+
+ first = !(*reenq_flags & SCX_REENQ_TSR_NOT_FIRST);
+ *reenq_flags |= SCX_REENQ_TSR_NOT_FIRST;
+
*reason = SCX_TASK_REENQ_KFUNC;
+
+ if ((p->scx.flags & SCX_TASK_IMMED) &&
+ (!first || !(*reenq_flags & SCX_REENQ_TSR_RQ_OPEN))) {
+ __scx_add_event(scx_task_sched(p), SCX_EV_REENQ_IMMED, 1);
+ *reason = SCX_TASK_REENQ_IMMED;
+ return true;
+ }
+
return *reenq_flags & SCX_REENQ_ANY;
}
@@ -3739,6 +3939,11 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
lockdep_assert_rq_held(rq);
+ if (WARN_ON_ONCE(reenq_flags & __SCX_REENQ_TSR_MASK))
+ reenq_flags &= ~__SCX_REENQ_TSR_MASK;
+ if (rq_is_open(rq, 0))
+ reenq_flags |= SCX_REENQ_TSR_RQ_OPEN;
+
/*
* The BPF scheduler may choose to dispatch tasks back to
* @rq->scx.local_dsq. Move all candidate tasks off to a private list
@@ -3792,11 +3997,14 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
static void process_deferred_reenq_locals(struct rq *rq)
{
+ u64 seq = ++rq->scx.deferred_reenq_locals_seq;
+
lockdep_assert_rq_held(rq);
while (true) {
struct scx_sched *sch;
u64 reenq_flags;
+ bool skip = false;
scoped_guard (raw_spinlock, &rq->scx.deferred_reenq_lock) {
struct scx_deferred_reenq_local *drl =
@@ -3811,15 +4019,31 @@ static void process_deferred_reenq_locals(struct rq *rq)
sch_pcpu = container_of(drl, struct scx_sched_pcpu,
deferred_reenq_local);
sch = sch_pcpu->sch;
+
reenq_flags = drl->flags;
WRITE_ONCE(drl->flags, 0);
list_del_init(&drl->node);
+
+ if (likely(drl->seq != seq)) {
+ drl->seq = seq;
+ drl->cnt = 0;
+ } else {
+ if (unlikely(++drl->cnt > SCX_REENQ_LOCAL_MAX_REPEAT)) {
+ scx_error(sch, "SCX_ENQ_REENQ on SCX_DSQ_LOCAL repeated %u times",
+ drl->cnt);
+ skip = true;
+ }
+
+ __scx_add_event(sch, SCX_EV_REENQ_LOCAL_REPEAT, 1);
+ }
}
- /* see schedule_dsq_reenq() */
- smp_mb();
+ if (!skip) {
+ /* see schedule_dsq_reenq() */
+ smp_mb();
- reenq_local(sch, rq, reenq_flags);
+ reenq_local(sch, rq, reenq_flags);
+ }
}
}
@@ -4208,10 +4432,6 @@ static void scx_cgroup_unlock(void) {}
/*
* Omitted operations:
*
- * - wakeup_preempt: NOOP as it isn't useful in the wakeup path because the task
- * isn't tied to the CPU at that point. Preemption is implemented by resetting
- * the victim task's slice to 0 and triggering reschedule on the target CPU.
- *
* - migrate_task_rq: Unnecessary as task to cpu mapping is transient.
*
* - task_fork/dead: We need fork/dead notifications for all tasks regardless of
@@ -4580,6 +4800,8 @@ static ssize_t scx_attr_events_show(struct kobject *kobj,
at += scx_attr_event_show(buf, at, &events, SCX_EV_DISPATCH_KEEP_LAST);
at += scx_attr_event_show(buf, at, &events, SCX_EV_ENQ_SKIP_EXITING);
at += scx_attr_event_show(buf, at, &events, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
+ at += scx_attr_event_show(buf, at, &events, SCX_EV_REENQ_IMMED);
+ at += scx_attr_event_show(buf, at, &events, SCX_EV_REENQ_LOCAL_REPEAT);
at += scx_attr_event_show(buf, at, &events, SCX_EV_REFILL_SLICE_DFL);
at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_DURATION);
at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_DISPATCH);
@@ -6019,6 +6241,8 @@ static void scx_dump_state(struct scx_sched *sch, struct scx_exit_info *ei,
scx_dump_event(s, &events, SCX_EV_DISPATCH_KEEP_LAST);
scx_dump_event(s, &events, SCX_EV_ENQ_SKIP_EXITING);
scx_dump_event(s, &events, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
+ scx_dump_event(s, &events, SCX_EV_REENQ_IMMED);
+ scx_dump_event(s, &events, SCX_EV_REENQ_LOCAL_REPEAT);
scx_dump_event(s, &events, SCX_EV_REFILL_SLICE_DFL);
scx_dump_event(s, &events, SCX_EV_BYPASS_DURATION);
scx_dump_event(s, &events, SCX_EV_BYPASS_DISPATCH);
@@ -7532,6 +7756,13 @@ void __init init_sched_ext_class(void)
*/
static bool scx_vet_enq_flags(struct scx_sched *sch, u64 dsq_id, u64 enq_flags)
{
+ if ((enq_flags & SCX_ENQ_IMMED) &&
+ unlikely(dsq_id != SCX_DSQ_LOCAL &&
+ (dsq_id & SCX_DSQ_LOCAL_ON) != SCX_DSQ_LOCAL_ON)) {
+ scx_error(sch, "SCX_ENQ_IMMED on a non-local DSQ 0x%llx", dsq_id);
+ return false;
+ }
+
return true;
}
@@ -9101,6 +9332,8 @@ static void scx_read_events(struct scx_sched *sch, struct scx_event_stats *event
scx_agg_event(events, e_cpu, SCX_EV_DISPATCH_KEEP_LAST);
scx_agg_event(events, e_cpu, SCX_EV_ENQ_SKIP_EXITING);
scx_agg_event(events, e_cpu, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);
+ scx_agg_event(events, e_cpu, SCX_EV_REENQ_IMMED);
+ scx_agg_event(events, e_cpu, SCX_EV_REENQ_LOCAL_REPEAT);
scx_agg_event(events, e_cpu, SCX_EV_REFILL_SLICE_DFL);
scx_agg_event(events, e_cpu, SCX_EV_BYPASS_DURATION);
scx_agg_event(events, e_cpu, SCX_EV_BYPASS_DISPATCH);
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index c78dadaadab8..2ef855f7c861 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -31,6 +31,8 @@ enum scx_consts {
SCX_BYPASS_LB_MIN_DELTA_DIV = 4,
SCX_BYPASS_LB_BATCH = 256,
+ SCX_REENQ_LOCAL_MAX_REPEAT = 256,
+
SCX_SUB_MAX_DEPTH = 4,
};
@@ -887,6 +889,24 @@ struct scx_event_stats {
*/
s64 SCX_EV_ENQ_SKIP_MIGRATION_DISABLED;
+ /*
+ * The number of times a task, enqueued on a local DSQ with
+ * SCX_ENQ_IMMED, was re-enqueued because the CPU was not available for
+ * immediate execution.
+ */
+ s64 SCX_EV_REENQ_IMMED;
+
+ /*
+ * The number of times a reenq of local DSQ caused another reenq of
+ * local DSQ. This can happen when %SCX_ENQ_IMMED races against a higher
+ * priority class task even if the BPF scheduler always satisfies the
+ * prerequisites for %SCX_ENQ_IMMED at the time of enqueue. However,
+ * that scenario is very unlikely and this count going up regularly
+ * indicates that the BPF scheduler is handling %SCX_ENQ_REENQ
+ * incorrectly causing recursive reenqueues.
+ */
+ s64 SCX_EV_REENQ_LOCAL_REPEAT;
+
/*
* Total number of times a task's time slice was refilled with the
* default value (SCX_SLICE_DFL).
@@ -951,6 +971,8 @@ struct scx_dsp_ctx {
struct scx_deferred_reenq_local {
struct list_head node;
u64 flags;
+ u64 seq;
+ u32 cnt;
};
struct scx_sched_pcpu {
@@ -1074,6 +1096,24 @@ enum scx_enq_flags {
*/
SCX_ENQ_PREEMPT = 1LLU << 32,
+ /*
+ * Only allowed on local DSQs. Guarantees that the task either gets
+ * on the CPU immediately and stays on it, or gets reenqueued back
+ * to the BPF scheduler. It will never linger on a local DSQ or be
+ * silently put back after preemption.
+ *
+ * The protection persists until the next fresh enqueue - it
+ * survives SAVE/RESTORE cycles, slice extensions and preemption.
+ * If the task can't stay on the CPU for any reason, it gets
+ * reenqueued back to the BPF scheduler.
+ *
+ * Exiting and migration-disabled tasks bypass ops.enqueue() and
+ * are placed directly on a local DSQ without IMMED protection
+ * unless %SCX_OPS_ENQ_EXITING and %SCX_OPS_ENQ_MIGRATION_DISABLED
+ * are set respectively.
+ */
+ SCX_ENQ_IMMED = 1LLU << 33,
+
/*
* The task being enqueued was previously enqueued on a DSQ, but was
* removed and is being re-enqueued. See SCX_TASK_REENQ_* flags to find
@@ -1098,6 +1138,7 @@ enum scx_enq_flags {
SCX_ENQ_CLEAR_OPSS = 1LLU << 56,
SCX_ENQ_DSQ_PRIQ = 1LLU << 57,
SCX_ENQ_NESTED = 1LLU << 58,
+ SCX_ENQ_GDSQ_FALLBACK = 1LLU << 59, /* fell back to global DSQ */
};
enum scx_deq_flags {
@@ -1127,6 +1168,12 @@ enum scx_reenq_flags {
__SCX_REENQ_FILTER_MASK = 0xffffLLU,
__SCX_REENQ_USER_MASK = SCX_REENQ_ANY,
+
+ /* bits 32-35 used by task_should_reenq() */
+ SCX_REENQ_TSR_RQ_OPEN = 1LLU << 32,
+ SCX_REENQ_TSR_NOT_FIRST = 1LLU << 33,
+
+ __SCX_REENQ_TSR_MASK = 0xfLLU << 32,
};
enum scx_pick_idle_cpu_flags {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 60627119d0ab..5b93f6190d31 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -800,6 +800,7 @@ struct scx_rq {
u32 cpuperf_target; /* [0, SCHED_CAPACITY_SCALE] */
bool cpu_released;
u32 flags;
+ u32 nr_immed; /* ENQ_IMMED tasks on local_dsq */
u64 clock; /* current per-rq clock -- see scx_bpf_now() */
cpumask_var_t cpus_to_kick;
cpumask_var_t cpus_to_kick_if_idle;
@@ -810,6 +811,7 @@ struct scx_rq {
struct task_struct *sub_dispatch_prev;
raw_spinlock_t deferred_reenq_lock;
+ u64 deferred_reenq_locals_seq;
struct list_head deferred_reenq_locals; /* scheds requesting reenq of local DSQ */
struct list_head deferred_reenq_users; /* user DSQs requesting reenq */
struct balance_callback deferred_bal_cb;
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index 704728864d83..cba37432eec0 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -404,6 +404,11 @@ static inline void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags)
scx_bpf_error("kernel too old to reenqueue foreign local or user DSQs");
}
+/*
+ * v7.1: %SCX_ENQ_IMMED.
+ */
+#define SCX_ENQ_IMMED __COMPAT_ENUM_OR_ZERO(enum scx_enq_flags, SCX_ENQ_IMMED)
+
/*
* Define sched_ext_ops. This may be expanded to define multiple variants for
* backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH().
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH 3/6] sched_ext: Implement SCX_ENQ_IMMED
2026-03-13 11:31 ` [PATCH 3/6] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
@ 2026-03-13 19:15 ` Andrea Righi
0 siblings, 0 replies; 11+ messages in thread
From: Andrea Righi @ 2026-03-13 19:15 UTC (permalink / raw)
To: Tejun Heo
Cc: David Vernet, Changwoo Min, sched-ext, Emil Tsalapatis,
linux-kernel
Hi Tejun,
On Fri, Mar 13, 2026 at 01:31:11AM -1000, Tejun Heo wrote:
> Add SCX_ENQ_IMMED enqueue flag for local DSQ insertions. Once a task is
> dispatched with IMMED, it either gets on the CPU immediately and stays on it,
> or gets reenqueued back to the BPF scheduler. It will never linger on a local
> DSQ behind other tasks or on a CPU taken by a higher-priority class.
>
> rq_is_open() uses rq->next_class to determine whether the rq is available,
> and wakeup_preempt_scx() triggers reenqueue when a higher-priority class task
> arrives. These capture all higher class preemptions. Combined with reenqueue
> points in the dispatch path, all cases where an IMMED task would not execute
> immediately are covered.
>
> SCX_TASK_IMMED persists in p->scx.flags until the next fresh enqueue, so the
> guarantee survives SAVE/RESTORE cycles. If preempted while running,
> put_prev_task_scx() reenqueues through ops.enqueue() with
> SCX_TASK_REENQ_PREEMPTED instead of silently placing the task back on the
> local DSQ.
>
> This enables tighter scheduling latency control by preventing tasks from
> piling up on local DSQs. It also enables opportunistic CPU sharing across
> sub-schedulers - without this, a sub-scheduler can stuff the local DSQ of a
> shared CPU, making it difficult for others to use.
>
> v2: - Rewrite is_curr_done() as rq_is_open() using rq->next_class and
> implement wakeup_preempt_scx() to achieve complete coverage of all
> cases where IMMED tasks could get stranded.
> - Track IMMED persistently in p->scx.flags and reenqueue
> preempted-while-running tasks through ops.enqueue().
> - Bound deferred reenq cycles (SCX_REENQ_LOCAL_MAX_REPEAT).
> - Misc renames, documentation.
>
> Signed-off-by: Tejun Heo <tj@kernel.org>
...
> diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
> index 2f59265b9b57..85cdb65a5a66 100644
> --- a/kernel/sched/ext.c
> +++ b/kernel/sched/ext.c
> @@ -406,6 +406,62 @@ static bool bypass_dsp_enabled(struct scx_sched *sch)
> return unlikely(atomic_read(&sch->bypass_dsp_enable_depth));
> }
>
> +/**
> + * rq_is_open - Is the rq available for immediate execution of an SCX task?
> + * @rq: rq to test
> + * @enq_flags: optional %SCX_ENQ_* of the task being enqueued
> + *
> + * Returns %true if @rq is currently open for executing an SCX task. After a
> + * %false return, @rq is guaranateed to invoke SCX dispatch path at least once
nit: s/guaranateed/guaranteed/
Thanks,
-Andrea
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH 4/6] sched_ext: Plumb enq_flags through the consume path
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (2 preceding siblings ...)
2026-03-13 11:31 ` [PATCH 3/6] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
@ 2026-03-13 11:31 ` Tejun Heo
2026-03-13 11:31 ` [PATCH 5/6] sched_ext: Add enq_flags to scx_bpf_dsq_move_to_local() Tejun Heo
` (4 subsequent siblings)
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 11:31 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
Add enq_flags parameter to consume_dispatch_q() and consume_remote_task(),
passing it through to move_{local,remote}_task_to_local_dsq(). All callers
pass 0.
No functional change. This prepares for SCX_ENQ_IMMED support on the consume
path.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 21 +++++++++++----------
1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 85cdb65a5a66..9dd51f0c9a53 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2355,13 +2355,14 @@ static bool unlink_dsq_and_lock_src_rq(struct task_struct *p,
!WARN_ON_ONCE(src_rq != task_rq(p));
}
-static bool consume_remote_task(struct rq *this_rq, struct task_struct *p,
+static bool consume_remote_task(struct rq *this_rq,
+ struct task_struct *p, u64 enq_flags,
struct scx_dispatch_q *dsq, struct rq *src_rq)
{
raw_spin_rq_unlock(this_rq);
if (unlink_dsq_and_lock_src_rq(p, dsq, src_rq)) {
- move_remote_task_to_local_dsq(p, 0, src_rq, this_rq);
+ move_remote_task_to_local_dsq(p, enq_flags, src_rq, this_rq);
return true;
} else {
raw_spin_rq_unlock(src_rq);
@@ -2441,7 +2442,7 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
}
static bool consume_dispatch_q(struct scx_sched *sch, struct rq *rq,
- struct scx_dispatch_q *dsq)
+ struct scx_dispatch_q *dsq, u64 enq_flags)
{
struct task_struct *p;
retry:
@@ -2471,13 +2472,13 @@ static bool consume_dispatch_q(struct scx_sched *sch, struct rq *rq,
if (rq == task_rq) {
task_unlink_from_dsq(p, dsq);
- move_local_task_to_local_dsq(p, 0, dsq, rq);
+ move_local_task_to_local_dsq(p, enq_flags, dsq, rq);
raw_spin_unlock(&dsq->lock);
return true;
}
if (task_can_run_on_remote_rq(sch, p, rq, false)) {
- if (likely(consume_remote_task(rq, p, dsq, task_rq)))
+ if (likely(consume_remote_task(rq, p, enq_flags, dsq, task_rq)))
return true;
goto retry;
}
@@ -2491,7 +2492,7 @@ static bool consume_global_dsq(struct scx_sched *sch, struct rq *rq)
{
int node = cpu_to_node(cpu_of(rq));
- return consume_dispatch_q(sch, rq, &sch->pnode[node]->global_dsq);
+ return consume_dispatch_q(sch, rq, &sch->pnode[node]->global_dsq, 0);
}
/**
@@ -2727,7 +2728,7 @@ scx_dispatch_sched(struct scx_sched *sch, struct rq *rq,
if (bypass_dsp_enabled(sch)) {
/* if @sch is bypassing, only the bypass DSQs are active */
if (scx_bypassing(sch, cpu))
- return consume_dispatch_q(sch, rq, bypass_dsq(sch, cpu));
+ return consume_dispatch_q(sch, rq, bypass_dsq(sch, cpu), 0);
#ifdef CONFIG_EXT_SUB_SCHED
/*
@@ -2745,7 +2746,7 @@ scx_dispatch_sched(struct scx_sched *sch, struct rq *rq,
struct scx_sched_pcpu *pcpu = per_cpu_ptr(sch->pcpu, cpu);
if (!(pcpu->bypass_host_seq++ % SCX_BYPASS_HOST_NTH) &&
- consume_dispatch_q(sch, rq, bypass_dsq(sch, cpu))) {
+ consume_dispatch_q(sch, rq, bypass_dsq(sch, cpu), 0)) {
__scx_add_event(sch, SCX_EV_SUB_BYPASS_DISPATCH, 1);
return true;
}
@@ -2817,7 +2818,7 @@ scx_dispatch_sched(struct scx_sched *sch, struct rq *rq,
* scheduler's ops.dispatch() doesn't yield any tasks.
*/
if (bypass_dsp_enabled(sch))
- return consume_dispatch_q(sch, rq, bypass_dsq(sch, cpu));
+ return consume_dispatch_q(sch, rq, bypass_dsq(sch, cpu), 0);
return false;
}
@@ -8195,7 +8196,7 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id, const struct bpf_prog_aux
return false;
}
- if (consume_dispatch_q(sch, dspc->rq, dsq)) {
+ if (consume_dispatch_q(sch, dspc->rq, dsq, 0)) {
/*
* A successfully consumed task can be dequeued before it starts
* running while the CPU is trying to migrate other dispatched
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 5/6] sched_ext: Add enq_flags to scx_bpf_dsq_move_to_local()
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (3 preceding siblings ...)
2026-03-13 11:31 ` [PATCH 4/6] sched_ext: Plumb enq_flags through the consume path Tejun Heo
@ 2026-03-13 11:31 ` Tejun Heo
2026-03-13 11:31 ` [PATCH 6/6] sched_ext: Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag Tejun Heo
` (3 subsequent siblings)
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 11:31 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
scx_bpf_dsq_move_to_local() moves a task from a non-local DSQ to the
current CPU's local DSQ. This is an indirect way of dispatching to a local
DSQ and should support enq_flags like direct dispatches do - e.g.
SCX_ENQ_HEAD for head-of-queue insertion and SCX_ENQ_IMMED for immediate
execution guarantees.
Add scx_bpf_dsq_move_to_local___v2() with an enq_flags parameter. The
original becomes a v1 compat wrapper passing 0. The compat macro is updated
to a three-level chain: v2 (7.1+) -> v1 (current) -> scx_bpf_consume
(pre-rename). All in-tree BPF schedulers are updated to pass 0.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 21 ++++++++++++++++++---
tools/sched_ext/include/scx/compat.bpf.h | 15 ++++++++++-----
tools/sched_ext/scx_central.bpf.c | 4 ++--
tools/sched_ext/scx_cpu0.bpf.c | 2 +-
tools/sched_ext/scx_flatcg.bpf.c | 6 +++---
tools/sched_ext/scx_qmap.bpf.c | 4 ++--
tools/sched_ext/scx_sdt.bpf.c | 2 +-
tools/sched_ext/scx_simple.bpf.c | 2 +-
8 files changed, 38 insertions(+), 18 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 9dd51f0c9a53..553730836000 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -8160,9 +8160,11 @@ __bpf_kfunc void scx_bpf_dispatch_cancel(const struct bpf_prog_aux *aux)
* scx_bpf_dsq_move_to_local - move a task from a DSQ to the current CPU's local DSQ
* @dsq_id: DSQ to move task from
* @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ * @enq_flags: %SCX_ENQ_*
*
* Move a task from the non-local DSQ identified by @dsq_id to the current CPU's
- * local DSQ for execution. Can only be called from ops.dispatch().
+ * local DSQ for execution with @enq_flags applied. Can only be called from
+ * ops.dispatch().
*
* This function flushes the in-flight dispatches from scx_bpf_dsq_insert()
* before trying to move from the specified DSQ. It may also grab rq locks and
@@ -8171,7 +8173,8 @@ __bpf_kfunc void scx_bpf_dispatch_cancel(const struct bpf_prog_aux *aux)
* Returns %true if a task has been moved, %false if there isn't any task to
* move.
*/
-__bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id, const struct bpf_prog_aux *aux)
+__bpf_kfunc bool scx_bpf_dsq_move_to_local___v2(u64 dsq_id, u64 enq_flags,
+ const struct bpf_prog_aux *aux)
{
struct scx_dispatch_q *dsq;
struct scx_sched *sch;
@@ -8186,6 +8189,9 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id, const struct bpf_prog_aux
if (!scx_kf_allowed(sch, SCX_KF_DISPATCH))
return false;
+ if (!scx_vet_enq_flags(sch, SCX_DSQ_LOCAL, enq_flags))
+ return false;
+
dspc = &this_cpu_ptr(sch->pcpu)->dsp_ctx;
flush_dispatch_buf(sch, dspc->rq);
@@ -8196,7 +8202,7 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id, const struct bpf_prog_aux
return false;
}
- if (consume_dispatch_q(sch, dspc->rq, dsq, 0)) {
+ if (consume_dispatch_q(sch, dspc->rq, dsq, enq_flags)) {
/*
* A successfully consumed task can be dequeued before it starts
* running while the CPU is trying to migrate other dispatched
@@ -8210,6 +8216,14 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id, const struct bpf_prog_aux
}
}
+/*
+ * COMPAT: ___v2 was introduced in v7.1. Remove this and ___v2 tag in the future.
+ */
+__bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id, const struct bpf_prog_aux *aux)
+{
+ return scx_bpf_dsq_move_to_local___v2(dsq_id, 0, aux);
+}
+
/**
* scx_bpf_dsq_move_set_slice - Override slice when moving between DSQs
* @it__iter: DSQ iterator in progress
@@ -8353,6 +8367,7 @@ BTF_KFUNCS_START(scx_kfunc_ids_dispatch)
BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots, KF_IMPLICIT_ARGS)
BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel, KF_IMPLICIT_ARGS)
BTF_ID_FLAGS(func, scx_bpf_dsq_move_to_local, KF_IMPLICIT_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_dsq_move_to_local___v2, KF_IMPLICIT_ARGS)
BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_slice, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_vtime, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_dsq_move, KF_RCU)
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index cba37432eec0..83b3425e63b2 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -28,8 +28,11 @@ struct cgroup *scx_bpf_task_cgroup___new(struct task_struct *p) __ksym __weak;
*
* scx_bpf_dispatch_from_dsq() and friends were added during v6.12 by
* 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()").
+ *
+ * v7.1: scx_bpf_dsq_move_to_local___v2() to add @enq_flags.
*/
-bool scx_bpf_dsq_move_to_local___new(u64 dsq_id) __ksym __weak;
+bool scx_bpf_dsq_move_to_local___v2(u64 dsq_id, u64 enq_flags) __ksym __weak;
+bool scx_bpf_dsq_move_to_local___v1(u64 dsq_id) __ksym __weak;
void scx_bpf_dsq_move_set_slice___new(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak;
void scx_bpf_dsq_move_set_vtime___new(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak;
bool scx_bpf_dsq_move___new(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
@@ -41,10 +44,12 @@ void scx_bpf_dispatch_from_dsq_set_vtime___old(struct bpf_iter_scx_dsq *it__iter
bool scx_bpf_dispatch_from_dsq___old(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
bool scx_bpf_dispatch_vtime_from_dsq___old(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
-#define scx_bpf_dsq_move_to_local(dsq_id) \
- (bpf_ksym_exists(scx_bpf_dsq_move_to_local___new) ? \
- scx_bpf_dsq_move_to_local___new((dsq_id)) : \
- scx_bpf_consume___old((dsq_id)))
+#define scx_bpf_dsq_move_to_local(dsq_id, enq_flags) \
+ (bpf_ksym_exists(scx_bpf_dsq_move_to_local___v2) ? \
+ scx_bpf_dsq_move_to_local___v2((dsq_id), (enq_flags)) : \
+ (bpf_ksym_exists(scx_bpf_dsq_move_to_local___v1) ? \
+ scx_bpf_dsq_move_to_local___v1((dsq_id)) : \
+ scx_bpf_consume___old((dsq_id))))
#define scx_bpf_dsq_move_set_slice(it__iter, slice) \
(bpf_ksym_exists(scx_bpf_dsq_move_set_slice___new) ? \
diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c
index 1c2376b75b5d..399e8d3f8bec 100644
--- a/tools/sched_ext/scx_central.bpf.c
+++ b/tools/sched_ext/scx_central.bpf.c
@@ -214,13 +214,13 @@ void BPF_STRUCT_OPS(central_dispatch, s32 cpu, struct task_struct *prev)
}
/* look for a task to run on the central CPU */
- if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ_ID))
+ if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ_ID, 0))
return;
dispatch_to_cpu(central_cpu);
} else {
bool *gimme;
- if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ_ID))
+ if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ_ID, 0))
return;
gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids);
diff --git a/tools/sched_ext/scx_cpu0.bpf.c b/tools/sched_ext/scx_cpu0.bpf.c
index 9b67ab11b04c..0b1a7ce879b0 100644
--- a/tools/sched_ext/scx_cpu0.bpf.c
+++ b/tools/sched_ext/scx_cpu0.bpf.c
@@ -66,7 +66,7 @@ void BPF_STRUCT_OPS(cpu0_enqueue, struct task_struct *p, u64 enq_flags)
void BPF_STRUCT_OPS(cpu0_dispatch, s32 cpu, struct task_struct *prev)
{
if (cpu == 0)
- scx_bpf_dsq_move_to_local(DSQ_CPU0);
+ scx_bpf_dsq_move_to_local(DSQ_CPU0, 0);
}
s32 BPF_STRUCT_OPS_SLEEPABLE(cpu0_init)
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
index a8a9234bb41e..1351377f64d5 100644
--- a/tools/sched_ext/scx_flatcg.bpf.c
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -660,7 +660,7 @@ static bool try_pick_next_cgroup(u64 *cgidp)
goto out_free;
}
- if (!scx_bpf_dsq_move_to_local(cgid)) {
+ if (!scx_bpf_dsq_move_to_local(cgid, 0)) {
bpf_cgroup_release(cgrp);
stat_inc(FCG_STAT_PNC_EMPTY);
goto out_stash;
@@ -740,7 +740,7 @@ void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev)
goto pick_next_cgroup;
if (time_before(now, cpuc->cur_at + cgrp_slice_ns)) {
- if (scx_bpf_dsq_move_to_local(cpuc->cur_cgid)) {
+ if (scx_bpf_dsq_move_to_local(cpuc->cur_cgid, 0)) {
stat_inc(FCG_STAT_CNS_KEEP);
return;
}
@@ -780,7 +780,7 @@ void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev)
pick_next_cgroup:
cpuc->cur_at = now;
- if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ)) {
+ if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ, 0)) {
cpuc->cur_cgid = 0;
return;
}
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index a4a1b84fe359..6d34115cb8bd 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -395,7 +395,7 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
if (dispatch_highpri(false))
return;
- if (!nr_highpri_queued && scx_bpf_dsq_move_to_local(SHARED_DSQ))
+ if (!nr_highpri_queued && scx_bpf_dsq_move_to_local(SHARED_DSQ, 0))
return;
if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) {
@@ -460,7 +460,7 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
if (!batch || !scx_bpf_dispatch_nr_slots()) {
if (dispatch_highpri(false))
return;
- scx_bpf_dsq_move_to_local(SHARED_DSQ);
+ scx_bpf_dsq_move_to_local(SHARED_DSQ, 0);
return;
}
if (!cpuc->dsp_cnt)
diff --git a/tools/sched_ext/scx_sdt.bpf.c b/tools/sched_ext/scx_sdt.bpf.c
index 31b09958e8d5..10248b71ef02 100644
--- a/tools/sched_ext/scx_sdt.bpf.c
+++ b/tools/sched_ext/scx_sdt.bpf.c
@@ -643,7 +643,7 @@ void BPF_STRUCT_OPS(sdt_enqueue, struct task_struct *p, u64 enq_flags)
void BPF_STRUCT_OPS(sdt_dispatch, s32 cpu, struct task_struct *prev)
{
- scx_bpf_dsq_move_to_local(SHARED_DSQ);
+ scx_bpf_dsq_move_to_local(SHARED_DSQ, 0);
}
s32 BPF_STRUCT_OPS_SLEEPABLE(sdt_init_task, struct task_struct *p,
diff --git a/tools/sched_ext/scx_simple.bpf.c b/tools/sched_ext/scx_simple.bpf.c
index b456bd7cae77..9ad6f0949987 100644
--- a/tools/sched_ext/scx_simple.bpf.c
+++ b/tools/sched_ext/scx_simple.bpf.c
@@ -89,7 +89,7 @@ void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags)
void BPF_STRUCT_OPS(simple_dispatch, s32 cpu, struct task_struct *prev)
{
- scx_bpf_dsq_move_to_local(SHARED_DSQ);
+ scx_bpf_dsq_move_to_local(SHARED_DSQ, 0);
}
void BPF_STRUCT_OPS(simple_running, struct task_struct *p)
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 6/6] sched_ext: Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (4 preceding siblings ...)
2026-03-13 11:31 ` [PATCH 5/6] sched_ext: Add enq_flags to scx_bpf_dsq_move_to_local() Tejun Heo
@ 2026-03-13 11:31 ` Tejun Heo
2026-03-13 18:37 ` [PATCH 7/6 sched_ext/for-7.1] sched_ext: Use schedule_deferred_locked() in schedule_dsq_reenq() Tejun Heo
` (2 subsequent siblings)
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 11:31 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
SCX_ENQ_IMMED makes enqueue to local DSQs succeed only if the task can start
running immediately. Otherwise, the task is re-enqueued through ops.enqueue().
This provides tighter control but requires specifying the flag on every
insertion.
Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag. When set, SCX_ENQ_IMMED is
automatically applied to all local DSQ enqueues including through
scx_bpf_dsq_move_to_local().
scx_qmap is updated with -I option to test the feature and -F option for
IMMED stress testing which forces every Nth enqueue to a busy local DSQ.
v2: - Cover scx_bpf_dsq_move_to_local() path (now has enq_flags via ___v2).
- scx_qmap: Remove sched_switch and cpu_release handlers (superseded by
kernel-side wakeup_preempt_scx()). Add -F for IMMED stress testing.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 31 +++++++------
kernel/sched/ext_internal.h | 9 +++-
tools/sched_ext/include/scx/compat.h | 1 +
tools/sched_ext/scx_qmap.bpf.c | 66 ++++++++++++----------------
tools/sched_ext/scx_qmap.c | 13 +++++-
5 files changed, 65 insertions(+), 55 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 553730836000..f7def0c57b51 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7755,20 +7755,25 @@ void __init init_sched_ext_class(void)
/********************************************************************************
* Helpers that can be called from the BPF scheduler.
*/
-static bool scx_vet_enq_flags(struct scx_sched *sch, u64 dsq_id, u64 enq_flags)
+static bool scx_vet_enq_flags(struct scx_sched *sch, u64 dsq_id, u64 *enq_flags)
{
- if ((enq_flags & SCX_ENQ_IMMED) &&
- unlikely(dsq_id != SCX_DSQ_LOCAL &&
- (dsq_id & SCX_DSQ_LOCAL_ON) != SCX_DSQ_LOCAL_ON)) {
- scx_error(sch, "SCX_ENQ_IMMED on a non-local DSQ 0x%llx", dsq_id);
- return false;
+ bool is_local = dsq_id == SCX_DSQ_LOCAL ||
+ (dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON;
+
+ if (*enq_flags & SCX_ENQ_IMMED) {
+ if (unlikely(!is_local)) {
+ scx_error(sch, "SCX_ENQ_IMMED on a non-local DSQ 0x%llx", dsq_id);
+ return false;
+ }
+ } else if ((sch->ops.flags & SCX_OPS_ALWAYS_ENQ_IMMED) && is_local) {
+ *enq_flags |= SCX_ENQ_IMMED;
}
return true;
}
static bool scx_dsq_insert_preamble(struct scx_sched *sch, struct task_struct *p,
- u64 dsq_id, u64 enq_flags)
+ u64 dsq_id, u64 *enq_flags)
{
if (!scx_kf_allowed(sch, SCX_KF_ENQUEUE | SCX_KF_DISPATCH))
return false;
@@ -7780,8 +7785,8 @@ static bool scx_dsq_insert_preamble(struct scx_sched *sch, struct task_struct *p
return false;
}
- if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
- scx_error(sch, "invalid enq_flags 0x%llx", enq_flags);
+ if (unlikely(*enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
+ scx_error(sch, "invalid enq_flags 0x%llx", *enq_flags);
return false;
}
@@ -7875,7 +7880,7 @@ __bpf_kfunc bool scx_bpf_dsq_insert___v2(struct task_struct *p, u64 dsq_id,
if (unlikely(!sch))
return false;
- if (!scx_dsq_insert_preamble(sch, p, dsq_id, enq_flags))
+ if (!scx_dsq_insert_preamble(sch, p, dsq_id, &enq_flags))
return false;
if (slice)
@@ -7901,7 +7906,7 @@ __bpf_kfunc void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id,
static bool scx_dsq_insert_vtime(struct scx_sched *sch, struct task_struct *p,
u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags)
{
- if (!scx_dsq_insert_preamble(sch, p, dsq_id, enq_flags))
+ if (!scx_dsq_insert_preamble(sch, p, dsq_id, &enq_flags))
return false;
if (slice)
@@ -8028,7 +8033,7 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
!scx_kf_allowed(sch, SCX_KF_DISPATCH))
return false;
- if (!scx_vet_enq_flags(sch, dsq_id, enq_flags))
+ if (!scx_vet_enq_flags(sch, dsq_id, &enq_flags))
return false;
/*
@@ -8189,7 +8194,7 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local___v2(u64 dsq_id, u64 enq_flags,
if (!scx_kf_allowed(sch, SCX_KF_DISPATCH))
return false;
- if (!scx_vet_enq_flags(sch, SCX_DSQ_LOCAL, enq_flags))
+ if (!scx_vet_enq_flags(sch, SCX_DSQ_LOCAL, &enq_flags))
return false;
dspc = &this_cpu_ptr(sch->pcpu)->dsp_ctx;
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 2ef855f7c861..b4f36d8b9c1d 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -182,13 +182,20 @@ enum scx_ops_flags {
*/
SCX_OPS_BUILTIN_IDLE_PER_NODE = 1LLU << 6,
+ /*
+ * If set, %SCX_ENQ_IMMED is assumed to be set on all local DSQ
+ * enqueues.
+ */
+ SCX_OPS_ALWAYS_ENQ_IMMED = 1LLU << 7,
+
SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE |
SCX_OPS_ENQ_LAST |
SCX_OPS_ENQ_EXITING |
SCX_OPS_ENQ_MIGRATION_DISABLED |
SCX_OPS_ALLOW_QUEUED_WAKEUP |
SCX_OPS_SWITCH_PARTIAL |
- SCX_OPS_BUILTIN_IDLE_PER_NODE,
+ SCX_OPS_BUILTIN_IDLE_PER_NODE |
+ SCX_OPS_ALWAYS_ENQ_IMMED,
/* high 8 bits are internal, don't include in SCX_OPS_ALL_FLAGS */
__SCX_OPS_INTERNAL_MASK = 0xffLLU << 56,
diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index 50297d4b9533..9e0c8f3161e8 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -116,6 +116,7 @@ static inline bool __COMPAT_struct_has_field(const char *type, const char *field
#define SCX_OPS_ENQ_MIGRATION_DISABLED SCX_OPS_FLAG(SCX_OPS_ENQ_MIGRATION_DISABLED)
#define SCX_OPS_ALLOW_QUEUED_WAKEUP SCX_OPS_FLAG(SCX_OPS_ALLOW_QUEUED_WAKEUP)
#define SCX_OPS_BUILTIN_IDLE_PER_NODE SCX_OPS_FLAG(SCX_OPS_BUILTIN_IDLE_PER_NODE)
+#define SCX_OPS_ALWAYS_ENQ_IMMED SCX_OPS_FLAG(SCX_OPS_ALWAYS_ENQ_IMMED)
#define SCX_PICK_IDLE_FLAG(name) __COMPAT_ENUM_OR_ZERO("scx_pick_idle_cpu_flags", #name)
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 6d34115cb8bd..f3587fb709c9 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -11,8 +11,6 @@
*
* - BPF-side queueing using PIDs.
* - Sleepable per-task storage allocation using ops.prep_enable().
- * - Using ops.cpu_release() to handle a higher priority scheduling class taking
- * the CPU away.
* - Core-sched support.
*
* This scheduler is primarily for demonstration and testing of sched_ext
@@ -47,6 +45,8 @@ const volatile bool print_msgs;
const volatile u64 sub_cgroup_id;
const volatile s32 disallow_tgid;
const volatile bool suppress_dump;
+const volatile bool always_enq_immed;
+const volatile u32 immed_stress_nth;
u64 nr_highpri_queued;
u32 test_error_cnt;
@@ -144,8 +144,10 @@ static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu)
{
s32 cpu;
- if (p->nr_cpus_allowed == 1 ||
- scx_bpf_test_and_clear_cpu_idle(prev_cpu))
+ if (!always_enq_immed && p->nr_cpus_allowed == 1)
+ return prev_cpu;
+
+ if (scx_bpf_test_and_clear_cpu_idle(prev_cpu))
return prev_cpu;
cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
@@ -238,6 +240,22 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
*/
tctx->core_sched_seq = core_sched_tail_seqs[idx]++;
+ /*
+ * IMMED stress testing: Every immed_stress_nth'th enqueue, dispatch
+ * directly to prev_cpu's local DSQ even when busy to force dsq->nr > 1
+ * and exercise the kernel IMMED reenqueue trigger paths.
+ */
+ if (immed_stress_nth && !(enq_flags & SCX_ENQ_REENQ)) {
+ static u32 immed_stress_cnt;
+
+ if (!(++immed_stress_cnt % immed_stress_nth)) {
+ tctx->force_local = false;
+ scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | scx_bpf_task_cpu(p),
+ slice_ns, enq_flags);
+ return;
+ }
+ }
+
/*
* If qmap_select_cpu() is telling us to or this is the last runnable
* task on the CPU, enqueue locally.
@@ -558,40 +576,11 @@ bool BPF_STRUCT_OPS(qmap_core_sched_before,
return task_qdist(a) > task_qdist(b);
}
-SEC("tp_btf/sched_switch")
-int BPF_PROG(qmap_sched_switch, bool preempt, struct task_struct *prev,
- struct task_struct *next, unsigned long prev_state)
-{
- if (!__COMPAT_scx_bpf_reenqueue_local_from_anywhere())
- return 0;
-
- /*
- * If @cpu is taken by a higher priority scheduling class, it is no
- * longer available for executing sched_ext tasks. As we don't want the
- * tasks in @cpu's local dsq to sit there until @cpu becomes available
- * again, re-enqueue them into the global dsq. See %SCX_ENQ_REENQ
- * handling in qmap_enqueue().
- */
- switch (next->policy) {
- case 1: /* SCHED_FIFO */
- case 2: /* SCHED_RR */
- case 6: /* SCHED_DEADLINE */
- scx_bpf_reenqueue_local();
-
- /* trigger re-enqueue on CPU0 just to exercise LOCAL_ON */
- if (__COMPAT_has_generic_reenq())
- scx_bpf_dsq_reenq(SCX_DSQ_LOCAL_ON | 0, 0);
- }
-
- return 0;
-}
-
-void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args)
-{
- /* see qmap_sched_switch() to learn how to do this on newer kernels */
- if (!__COMPAT_scx_bpf_reenqueue_local_from_anywhere())
- scx_bpf_reenqueue_local();
-}
+/*
+ * sched_switch tracepoint and cpu_release handlers are no longer needed.
+ * With SCX_OPS_ALWAYS_ENQ_IMMED, wakeup_preempt_scx() reenqueues IMMED
+ * tasks when a higher-priority scheduling class takes the CPU.
+ */
s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p,
struct scx_init_task_args *args)
@@ -999,7 +988,6 @@ SCX_OPS_DEFINE(qmap_ops,
.dispatch = (void *)qmap_dispatch,
.tick = (void *)qmap_tick,
.core_sched_before = (void *)qmap_core_sched_before,
- .cpu_release = (void *)qmap_cpu_release,
.init_task = (void *)qmap_init_task,
.dump = (void *)qmap_dump,
.dump_cpu = (void *)qmap_dump_cpu,
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 5916bbe0d77f..e7c89a2bc3d8 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -21,7 +21,7 @@ const char help_fmt[] =
"See the top-level comment in .bpf.c for more details.\n"
"\n"
"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
-" [-P] [-M] [-H] [-d PID] [-D LEN] [-S] [-p] [-v]\n"
+" [-P] [-M] [-H] [-d PID] [-D LEN] [-S] [-p] [-I] [-F COUNT] [-v]\n"
"\n"
" -s SLICE_US Override slice duration\n"
" -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n"
@@ -36,6 +36,8 @@ const char help_fmt[] =
" -D LEN Set scx_exit_info.dump buffer length\n"
" -S Suppress qmap-specific debug dump\n"
" -p Switch only tasks on SCHED_EXT policy instead of all\n"
+" -I Turn on SCX_OPS_ALWAYS_ENQ_IMMED\n"
+" -F COUNT IMMED stress: force every COUNT'th enqueue to a busy local DSQ (use with -I)\n"
" -v Print libbpf debug messages\n"
" -h Display this help and exit\n";
@@ -68,7 +70,7 @@ int main(int argc, char **argv)
skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL");
- while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PMHc:d:D:Spvh")) != -1) {
+ while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PMHc:d:D:SpIF:vh")) != -1) {
switch (opt) {
case 's':
skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -121,6 +123,13 @@ int main(int argc, char **argv)
case 'p':
skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
break;
+ case 'I':
+ skel->rodata->always_enq_immed = true;
+ skel->struct_ops.qmap_ops->flags |= SCX_OPS_ALWAYS_ENQ_IMMED;
+ break;
+ case 'F':
+ skel->rodata->immed_stress_nth = strtoul(optarg, NULL, 0);
+ break;
case 'v':
verbose = true;
break;
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH 7/6 sched_ext/for-7.1] sched_ext: Use schedule_deferred_locked() in schedule_dsq_reenq()
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (5 preceding siblings ...)
2026-03-13 11:31 ` [PATCH 6/6] sched_ext: Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag Tejun Heo
@ 2026-03-13 18:37 ` Tejun Heo
2026-03-13 19:21 ` [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Andrea Righi
2026-03-13 19:45 ` Tejun Heo
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 18:37 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel, Tejun Heo
schedule_dsq_reenq() always uses schedule_deferred() which falls back to
irq_work. However, callers like schedule_reenq_local() already hold the
target rq lock, and scx_bpf_dsq_reenq() may hold it via the ops callback.
Add a locked_rq parameter so schedule_dsq_reenq() can use
schedule_deferred_locked() when the target rq is already held. The locked
variant can use cheaper paths (balance callbacks, wakeup hooks) instead of
always bouncing through irq_work.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 24 +++++++++++++++---------
1 file changed, 15 insertions(+), 9 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index f7def0c57b51..a87d99ffe1fe 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1218,8 +1218,10 @@ static void schedule_deferred_locked(struct rq *rq)
}
static void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
- u64 reenq_flags)
+ u64 reenq_flags, struct rq *locked_rq)
{
+ struct rq *rq;
+
/*
* Allowing reenqueues doesn't make sense while bypassing. This also
* blocks from new reenqueues to be scheduled on dead scheds.
@@ -1228,7 +1230,8 @@ static void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq
return;
if (dsq->id == SCX_DSQ_LOCAL) {
- struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
+ rq = container_of(dsq, struct rq, scx.local_dsq);
+
struct scx_sched_pcpu *sch_pcpu = per_cpu_ptr(sch->pcpu, cpu_of(rq));
struct scx_deferred_reenq_local *drl = &sch_pcpu->deferred_reenq_local;
@@ -1247,10 +1250,9 @@ static void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq
list_move_tail(&drl->node, &rq->scx.deferred_reenq_locals);
WRITE_ONCE(drl->flags, drl->flags | reenq_flags);
}
-
- schedule_deferred(rq);
} else if (!(dsq->id & SCX_DSQ_FLAG_BUILTIN)) {
- struct rq *rq = this_rq();
+ rq = this_rq();
+
struct scx_dsq_pcpu *dsq_pcpu = per_cpu_ptr(dsq->pcpu, cpu_of(rq));
struct scx_deferred_reenq_user *dru = &dsq_pcpu->deferred_reenq_user;
@@ -1269,11 +1271,15 @@ static void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq
list_move_tail(&dru->node, &rq->scx.deferred_reenq_users);
WRITE_ONCE(dru->flags, dru->flags | reenq_flags);
}
-
- schedule_deferred(rq);
} else {
scx_error(sch, "DSQ 0x%llx not allowed for reenq", dsq->id);
+ return;
}
+
+ if (rq == locked_rq)
+ schedule_deferred_locked(rq);
+ else
+ schedule_deferred(rq);
}
static void schedule_reenq_local(struct rq *rq, u64 reenq_flags)
@@ -1283,7 +1289,7 @@ static void schedule_reenq_local(struct rq *rq, u64 reenq_flags)
if (WARN_ON_ONCE(!root))
return;
- schedule_dsq_reenq(root, &rq->scx.local_dsq, reenq_flags);
+ schedule_dsq_reenq(root, &rq->scx.local_dsq, reenq_flags, rq);
}
/**
@@ -8845,7 +8851,7 @@ __bpf_kfunc void scx_bpf_dsq_reenq(u64 dsq_id, u64 reenq_flags,
reenq_flags |= SCX_REENQ_ANY;
dsq = find_dsq_for_dispatch(sch, this_rq(), dsq_id, smp_processor_id());
- schedule_dsq_reenq(sch, dsq, reenq_flags);
+ schedule_dsq_reenq(sch, dsq, reenq_flags, scx_locked_rq());
}
/**
--
2.53.0
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (6 preceding siblings ...)
2026-03-13 18:37 ` [PATCH 7/6 sched_ext/for-7.1] sched_ext: Use schedule_deferred_locked() in schedule_dsq_reenq() Tejun Heo
@ 2026-03-13 19:21 ` Andrea Righi
2026-03-13 19:45 ` Tejun Heo
8 siblings, 0 replies; 11+ messages in thread
From: Andrea Righi @ 2026-03-13 19:21 UTC (permalink / raw)
To: Tejun Heo
Cc: David Vernet, Changwoo Min, sched-ext, Emil Tsalapatis,
linux-kernel
On Fri, Mar 13, 2026 at 01:31:08AM -1000, Tejun Heo wrote:
> Hello,
>
> Currently, BPF schedulers that want to ensure tasks don't linger on local
> DSQs behind other tasks or on CPUs taken by higher-priority scheduling
> classes must resort to hooking the sched_switch tracepoint or implementing
> the now-deprecated ops.cpu_acquire/release(). Both approaches are cumbersome
> and partial - sched_switch doesn't handle cases where a local DSQ ends up
> with multiple tasks queued, which can be difficult to control perfectly.
> cpu_release() is even more limited, missing cases like a higher-priority
> task waking up while an idle CPU is waking up to an SCX task. Neither can
> atomically determine whether a CPU is truly available at the moment of
> dispatch.
>
> SCX_ENQ_IMMED replaces these with a single dispatch flag that provides a
> kernel-enforced guarantee: a task dispatched with IMMED either gets on the
> CPU immediately, or gets reenqueued back to the BPF scheduler. It will never
> linger on a local DSQ behind other tasks or be silently put back after
> preemption. This gives BPF schedulers comprehensive latency control directly
> in the dispatch path.
>
> The protection is persistent - it survives SAVE/RESTORE cycles, slice
> extensions and higher-priority class preemptions. If an IMMED task is
> preempted while running, it gets reenqueued through ops.enqueue() with
> SCX_TASK_REENQ_PREEMPTED instead of silently placed back on the local DSQ.
>
> This also enables opportunistic CPU sharing across sub-schedulers. Without
> IMMED, a sub-scheduler can stuff the local DSQ of a shared CPU, making it
> difficult for others to use. With IMMED, tasks only stay on a CPU when they
> can actually run, keeping CPUs available for other schedulers.
>
> Patches 1-2 are prep refactoring. Patch 3 implements SCX_ENQ_IMMED. Patches
> 4-5 plumb enq_flags through the consume and move_to_local paths so IMMED
> works on those paths too. Patch 6 adds SCX_OPS_ALWAYS_ENQ_IMMED.
>
> v2: - Split prep patches out of main IMMED patch (#1, #2).
> - Rewrite is_curr_done() as rq_is_open() using rq->next_class and
> implement wakeup_preempt_scx() for complete higher-class preemption
> coverage (#3).
> - Track IMMED persistently in p->scx.flags and reenqueue
> preempted-while-running tasks through ops.enqueue() (#3).
> - Drop "disallow setting slice to zero" patch - no longer needed with
> rq_is_open() approach.
> - Plumb enq_flags through consume and move_to_local paths (#4, #5).
> - Cover scx_bpf_dsq_move_to_local() in OPS_ALWAYS_IMMED (#6).
> - Remove obsolete sched_switch tracepoint and cpu_release handlers
> from scx_qmap, add IMMED stress test (#6) (Andrea Righi).
>
> v1: https://lore.kernel.org/r/20260307002817.1298341-1-tj@kernel.org
Only found a small typo in patch 3, everything else looks good to me.
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Thanks,
-Andrea
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED
2026-03-13 11:31 [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Tejun Heo
` (7 preceding siblings ...)
2026-03-13 19:21 ` [PATCHSET v2 sched_ext/for-7.1] sched_ext: Implement SCX_ENQ_IMMED Andrea Righi
@ 2026-03-13 19:45 ` Tejun Heo
8 siblings, 0 replies; 11+ messages in thread
From: Tejun Heo @ 2026-03-13 19:45 UTC (permalink / raw)
To: David Vernet, Andrea Righi, Changwoo Min
Cc: sched-ext, Emil Tsalapatis, linux-kernel
Hello,
> 1. sched_ext: Split task_should_reenq() into local and user variants
> 2. sched_ext: Add scx_vet_enq_flags() and plumb dsq_id into preamble
> 3. sched_ext: Implement SCX_ENQ_IMMED
> 4. sched_ext: Plumb enq_flags through the consume path
> 5. sched_ext: Add enq_flags to scx_bpf_dsq_move_to_local()
> 6. sched_ext: Add SCX_OPS_ALWAYS_ENQ_IMMED ops flag
> 7. sched_ext: Use schedule_deferred_locked() in schedule_dsq_reenq()
Applied 1-7 to sched_ext/for-7.1 with typo fix in #3 (guaranateed ->
guaranteed).
Thanks.
--
tejun
^ permalink raw reply [flat|nested] 11+ messages in thread